perf regs x86: Add X86 specific arch__intr_reg_mask()

XMM registers can be collected on Icelake and later platforms.

Add specific arch__intr_reg_mask(), which creating an event to check if
the kernel and hardware can collect XMM registers.

Test on Skylake which doesn't support XMM registers collection. There is
nothing changed.

   #perf record -I?
   available registers: AX BX CX DX SI DI BP SP IP FLAGS CS SS R8 R9
   R10 R11 R12 R13 R14 R15

   Usage: perf record [<options>] [<command>]
    or: perf record [<options>] -- <command> [<options>]

    -I, --intr-regs[=<any register>]
                          sample selected machine registers on
   interrupt, use '-I?' to list register names

   #perf record -I
   [ perf record: Woken up 1 times to write data ]
   [ perf record: Captured and wrote 0.905 MB perf.data (2520 samples) ]

   #perf evlist -v
   cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type:
   IP|TID|TIME|CPU|PERIOD|REGS_INTR, read_format: ID, disabled: 1,
   inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, precise_ip: 3,
   sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol:
   1, bpf_event: 1, sample_regs_intr: 0xff0fff

Test on Icelake which support XMM registers collection.

   #perf record -I?
   available registers: AX BX CX DX SI DI BP SP IP FLAGS CS SS R8 R9 R10
   R11 R12 R13 R14 R15 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 XMM9
   XMM10 XMM11 XMM12 XMM13 XMM14 XMM15

   Usage: perf record [<options>] [<command>]
    or: perf record [<options>] -- <command> [<options>]

    -I, --intr-regs[=<any register>]
                          sample selected machine registers on
   interrupt, use '-I?' to list register names

   #perf record -I
   [ perf record: Woken up 1 times to write data ]
   [ perf record: Captured and wrote 0.800 MB perf.data (318 samples) ]

   #perf evlist -v
   cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type:
   IP|TID|TIME|CPU|PERIOD|REGS_INTR, read_format: ID, disabled: 1,
   inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, precise_ip: 3,
   sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol:
   1, bpf_event: 1, sample_regs_intr: 0xffffffff00ff0fff

Committer notes:

Don't set attr.sample_period as a named struct init, as it is part of an
unnamed union in 'struct perf_event_attr', and doing so breaks the build
on older gcc versions, such as:

  gcc version 4.1.2 20080704 (Red Hat 4.1.2-55)
  gcc version 4.4.7 20120313 (Red Hat 4.4.7-23) (GCC)

  arch/x86/util/perf_regs.c: In function 'arch__intr_reg_mask':
  arch/x86/util/perf_regs.c:279: error: unknown field 'sample_period' specified in initializer
  cc1: warnings being treated as errors
  arch/x86/util/perf_regs.c:279: warning: missing braces around initializer
  arch/x86/util/perf_regs.c:279: warning: (near initialization for 'attr.<anonymous>')

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
[ Only on a lenovo t480s, a skylake machine, where the XMM registers didn't show up in -I?/--user-regs=? as expected ]
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/1557865174-56264-3-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/arch/x86/include/perf_regs.h

@@ -9,6 +9,7 @@
 void perf_regs_load(u64 *regs);
 
 #define PERF_REGS_MAX PERF_REG_X86_XMM_MAX
+#define PERF_XMM_REGS_MASK	(~((1ULL << PERF_REG_X86_XMM0) - 1))
 #ifndef HAVE_ARCH_X86_64_SUPPORT
 #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
 #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32

tools/perf/arch/x86/util/perf_regs.c

@@ -270,3 +270,31 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op)
 
 	return SDT_ARG_VALID;
 }
+
+uint64_t arch__intr_reg_mask(void)
+{
+	struct perf_event_attr attr = {
+		.type			= PERF_TYPE_HARDWARE,
+		.config			= PERF_COUNT_HW_CPU_CYCLES,
+		.sample_type		= PERF_SAMPLE_REGS_INTR,
+		.sample_regs_intr	= PERF_XMM_REGS_MASK,
+		.precise_ip		= 1,
+		.disabled 		= 1,
+		.exclude_kernel		= 1,
+	};
+	int fd;
+	/*
+	 * In an unnamed union, init it here to build on older gcc versions
+	 */
+	attr.sample_period = 1;
+
+	event_attr_init(&attr);
+
+	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+	if (fd != -1) {
+		close(fd);
+		return (PERF_XMM_REGS_MASK | PERF_REGS_MASK);
+	}
+
+	return PERF_REGS_MASK;
+}